|国家预印本平台
首页|BabyLM's First Constructions: Causal interventions provide a signal of learning

BabyLM's First Constructions: Causal interventions provide a signal of learning

BabyLM's First Constructions: Causal interventions provide a signal of learning

来源:Arxiv_logoArxiv
英文摘要

Construction grammar posits that children acquire constructions (form-meaning pairings) from the statistics of their environment. Recent work supports this hypothesis by showing sensitivity to constructions in pretrained language models (PLMs), including one recent study (Rozner et al., 2025) demonstrating that constructions shape the PLM's output distribution. However, models under study have generally been trained on developmentally implausible amounts of data, casting doubt on their relevance to human language learning. Here we use Rozner et al.'s methods to evaluate constructional learning in models from the 2024 BabyLM challenge. Our results show that even when trained on developmentally plausible quantities of data, models represent diverse constructions, even hard cases that are superficially indistinguishable. We further find correlational evidence that constructional performance may be functionally relevant: models that better represent constructions perform better on the BabyLM benchmarks.

Joshua Rozner、Leonie Weissweiler、Cory Shain

语言学

Joshua Rozner,Leonie Weissweiler,Cory Shain.BabyLM's First Constructions: Causal interventions provide a signal of learning[EB/OL].(2025-06-02)[2025-06-22].https://arxiv.org/abs/2506.02147.点此复制

评论